Build Qlik Pipelines with AI and VS Code

Name: Build Qlik Pipelines with AI and VS Code
Uploaded: 2026-08-11T09:08:45-04:00
Duration: 1 min 45 s
Description: Managing your data pipelines shouldn't mean leaving the tools you already work in. In this video, Qlik Solution Architect, Joe Easley, shows how Qlik's declarative pipelines let you build and manage your integration ecosystem right alongside your own...

Qlik

08/11/2026

0 (0%)

Report Like Favorite

TL;DR

Joe Easley demonstrates converting an existing Snowflake SQL pipeline into a declarative YAML pipeline in Qlik Talent Cloud using Claude and VS Code in under two minutes.
Claude generates the complete QTC project — source registration, storage task, and three data transforms — entirely from a SQL file and a short prompt, with no manual YAML authoring required.
The generated pipeline is committed to GitHub and applied to Qlik Talent Cloud via its native GitHub integration, keeping the entire workflow inside familiar developer tools.

Summary

In this short technical demonstration, Qlik Solutions Architect Joe Easley shows how developers can use AI-assisted tooling — specifically Claude as the LLM and VS Code as the IDE — to convert existing Snowflake SQL pipelines into fully declarative YAML-based pipelines in Qlik Talent Cloud (QTC). Starting from a plain SQL DDL and task file, Joe prompts Claude with a brief set of guidelines and lets it generate a complete QTC project in roughly two minutes. The output includes source registration, a storage task, and three separate transforms for activity, customer, and workload data — each with its own datasets and source selection — all expressed as declarative YAML without any manual authoring. The generated project is then committed to a GitHub repository and pulled into Qlik Talent Cloud via its native GitHub integration, resulting in a fully built, ready-to-run pipeline visible directly in the QTC interface. The demo emphasizes that developers never need to leave their preferred tools: the entire authoring and version-control workflow stays within VS Code and GitHub, with Qlik Talent Cloud consuming the output. This approach targets data engineers and developers who want faster pipeline iteration, reduced handoffs between teams, and pipelines that live natively alongside application code in source control.

Chapters

0:00 - Introduction and Overview
0:26 - Starting Point: SQL File and Claude Prompt
0:41 - AI-Generated QTC Project Output
1:04 - GitHub Commit and QTC Deployment

Key Quotes

0:19 "... rebuild it as a declarative pipeline in Qlik Talent Cloud, with VS Code and Claude doing the heavy lifting."
0:54 "All declarative YAML, none of it written by hand."
1:33 "And that's the whole loop, Snowflake SQL in, a working QTC pipeline out, in a fraction of the time it would take by hand."

FAQ

Do I need to learn a new UI to build pipelines in Qlik Talent Cloud using this approach?

No. The demonstration shows the entire pipeline being authored in VS Code with AI assistance, committed to GitHub, and then applied to Qlik Talent Cloud via its GitHub integration — no manual work inside the QTC interface is required.

What does the AI-generated output actually include?

Claude produced a complete QTC project containing source registration, a storage task, and three transforms (for activity, customer, and workload data), each with its own datasets and source selection — all as declarative YAML.

Categories:

» Cybersecurity » Application Security
» Data Protection

Tags:

Show more Show less

TL;DR

Summary

Chapters

Key Quotes

FAQ

Bridging the SaaS Protection Gap: Preventing Data Loss and AI Missteps

The Automation Escalation: Discovering the AI-Driven Underground Revolution

Invisible Data: Understanding What You Can't Safeguard